Self-motivated individual and looking for challenges
5 years industrial experiences as a data scientist
10+ years of experience in statistical modeling, machine learning and deep learning
15+ years software programming and database management experience
15+ first authored academic journal papers (data analysis oriented)
20+ presentations at regional and international conferences
Problem solver, team player, multitasker and improvement initiator
Overview
4
4
years of professional experience
1
1
Certification
Work History
Data Science Lead
MilliporeSigma
04.2022 - Current
Lead project "Deep learning driven retrosynthetic tool" from ground up, and collaborate with universities, external vendors, and internal groups to transform rule-based Synthia(TM) to data-driven Synthia(TM)
Write proposals to BlueHouse project, completed prototypes, and presented to stakeholders
Closely collaborate with AIDD (AI for Drug Discovery) to develop mini-version retro tools from ground up. Make data pipelines, build deep learning models and publish services in Google Cloud
Senior Data Scientist
Mercy Healthcare
12.2021 - 04.2022
Process mining in Healthcare (visualize process mining maps using Typescripts and explore visualization options to proof concepts)
Covid case prediction (predict number of infected healthcare workers in Mercy and predict Covid test lab utilization)
Mentored other members in data science group
Data Scientist
MilliporeSigma
07.2018 - 01.2020
Led chemical product recommender system to support sales in China. Used various machine learning and deep learning based recommendation models to implement multiple recommendation strategies
Led project "Predictive toxicity in-silico approach" (funded by Innovation Center, MilliporeSigma), and developed deep learning models and advanced learning strategies from ground up. Presented to innovation board and CEO
Initiator of "emerging terms detection in life science". Developed nature language processing (NLP) based tools and computational network algorithms to detect emerging terms. Presented to innovation board and CEO
Led project "Text mining platform", coordinated with UI/UX, software development, and data science groups ; organized project meetings and tracked progress
Led project "deep learning based imaging processing". Used Autoencoder to detect CPE infected plates
Leadership work: hosted data science group meetings and take meeting minutes; drafted data science and bioinformatics related job description; served as technical interviewee; presented at internal conferences; mentored two (2) interns
Postdoc Research
University Of South Florida
01.2017 - 06.2018
Performed big data analysis in connected vehicle setting
Worked with USDOT and relevant stakeholders
Education
Ph.D. - System Industrial Engineering
University of Arizona
Tucson, AZ
12.2016
Master of Science - Geographical Information System
Southeast University
China
05.2012
Skills
Deep learning
Fully connected NN
Conv NN, Graph CNN
GAN
Transfer learning
Machine learning
Natural language processing
Stats modeling
Certification
2022, Microsoft Azure Fundamentals certification (Certification ID: 12336649)
2007, Licensed Database Management System Engineer (Registration ID: 07145320135), awarded by the Ministry of Industry and Information Technology of the People’s Republic of China
2006, Licensed Software Engineer (Registration ID: 06218320501), awarded by the Ministry of Industry and Information Technology of the People’s Republic of China
Timeline
Data Science Lead
MilliporeSigma
04.2022 - Current
Senior Data Scientist
Mercy Healthcare
12.2021 - 04.2022
Data Scientist
MilliporeSigma
07.2018 - 01.2020
Postdoc Research
University Of South Florida
01.2017 - 06.2018
Ph.D. - System Industrial Engineering
University of Arizona
Master of Science - Geographical Information System